QAT(quantize aware training) for classification with MQBench

Last update: Nov 18, 2022

Overview

MQBench Quantization Aware Training with PyTorch

I am using MQBench(Model Quantization Benchmark)(http://mqbench.tech/) to quantize the model for deployment.

MQBench is a benchmark and framework for evluating the quantization algorithms under real world hardware deployments.

Prerequisites

Python 3.7+
PyTorch 1.8.1+

Install MQBench Lib

Before run this repository, you should install MQBench:

git clone https://github.com/ModelTC/MQBench.git
cd MQBench
python setup.py build
python setup.py install

Training Fp32 Model

# Start training fp32 model with: 
# model_name can be ResNet18, MobileNet, ...
python main.py model_name

# You can manually config the training with: 
python main.py --resume --lr=0.01

Training Quantize Model

# Start training quantize model with: 
# model_name can be ResNet18, MobileNet, ...
python main.py model_name --quantize

# You can manually config the training with: 
python main.py --resume --parallel DP --BackendType Tensorrt --quantize
python -m torch.distributed.launch main.py --local_rank 0 --parallel DDP --resume  --BackendType Tensorrt --quantize

Fp32 Accuracy

Model	Acc.
VGG16	92.64%
ResNet18	93.02%
ResNet50	93.62%
ResNet101	93.75%
RegNetX_200MF	94.24%
RegNetY_400MF	94.29%
MobileNetV2	94.43%
ResNeXt29(32x4d)	94.73%
ResNeXt29(2x64d)	94.82%
SimpleDLA	94.89%
DenseNet121	95.04%
PreActResNet18	95.11%
DPN92	95.16%
DLA	95.47%

QAT(quantize aware training) for classification with MQBench

Related tags

Overview

MQBench Quantization Aware Training with PyTorch

Prerequisites

Install MQBench Lib

Training Fp32 Model

Training Quantize Model

Fp32 Accuracy

Owner

Ling Zhang

TorchOk - The toolkit for fast Deep Learning experiments in Computer Vision

This code finds bounding box of a single human mouth.

A curated list of awesome Active Learning

This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

Tweesent-back - Tweesent backend uses fastAPI as the web framework

LeafSnap replicated using deep neural networks to test accuracy compared to traditional computer vision methods.

git《Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction》(ECCV 2020) GitHub:

A Python library that provides a simplified alternative to DBAPI 2

Аналитика доходности инвестиционного портфеля в Тинькофф брокере

Code accompanying the NeurIPS 2021 paper "Generating High-Quality Explanations for Navigation in Partially-Revealed Environments"

Repo for the paper Extrapolating from a Single Image to a Thousand Classes using Distillation

Deep Convolutional Generative Adversarial Networks

Asynchronous Advantage Actor-Critic in PyTorch

PyTorch implementation for "Mining Latent Structures with Contrastive Modality Fusion for Multimedia Recommendation"

Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations

Pytorch Lightning code guideline for conferences

Minimal fastai code needed for working with pytorch

Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary Differential Equations

Immortal tracker

PyTorch implementation of paper: AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer, ICCV 2021.